Abstract: Methods and systems for creating TEM lamella using image restoration algorithms for low keV FIB images are disclosed. An example method includes irradiating a sample with an ion beam at low keV settings, generating a low keV ion beam image of the sample based on emissions resultant from irradiation by the ion beam, and then applying an image restoration model to the low keV ion beam image of the sample to generate a restored image. The sample is then localized within the restored image, and a low keV milling of the sample is performed with the ion beam based on the localized sample within the restored image.

Abstract: Techniques for adapting an adaptive specimen image acquisition system using an artificial neural network (ANN) are disclosed. An adaptive specimen image acquisition system is configurable to scan a specimen to produce images of varying qualities. An adaptive specimen image acquisition system first scans a specimen to produce a low-quality image. An ANN identifies objects of interest within the specimen image. A scan mask indicates regions of the image corresponding to the objects of interest. The adaptive specimen image acquisition system scans only the regions of the image corresponding to the objects of interest, as indicated by the scan mask, to produce a high-quality image. The low-quality image and the high-quality image are merged in a final image. The final image shows the objects of interest at a higher quality, and the rest of the specimen at a lower quality.

Abstract: Techniques for training an artificial neural network (ANN) using simulated specimen images are described. Simulated specimen images are generated based on data models. The data models describe characteristics of a crystalline material and characteristics of one or more defect types. The data models do not include any image data. Simulated specimen images are input as training data into a training algorithm to generate an artificial neural network (ANN) for identifying defects in crystalline materials. After the ANN is trained, the ANN analyzes captured specimen images to identify defects shown therein.

Abstract: The present invention relates to a method of training a network for reconstructing and/or segmenting microscopic images comprising the step of training the network in the cloud. Further, for training the network in the cloud training data comprising microscopic images can be uploaded into the cloud and a network is trained by the microscopic images. Moreover, for training the network the network can be benchmarked after the reconstructing and/or segmenting of the microscopic images. Wherein for benchmarking the network the quality of the image(s) having undergone the reconstructing and/or segmenting by the network can be compared with the quality of the image(s) having undergone reconstructing and/or segmenting by already known algorithm and/or a second network.

Abstract: Techniques for training an artificial neural network (ANN) using simulated specimen images are described. Simulated specimen images are generated based on data models. The data models describe characteristics of a crystalline material and characteristics of one or more defect types. The data models do not include any image data. Simulated specimen images are input as training data into a training algorithm to generate an artificial neural network (ANN) for identifying defects in crystalline materials. After the ANN is trained, the ANN analyzes captured specimen images to identify defects shown therein.

Abstract: Methods and systems for neural network based image restoration are disclosed herein. An example method at least includes acquiring a plurality of training image pairs of a sample, where each training image of each of the plurality of training image pairs are images of a same location of a sample, and where each image of the plurality of training image pairs are acquired using same acquisition parameters, updating an artificial neural network based on the plurality of training image pairs, and denoising a plurality of sample images using the updated artificial neural network, where the plurality of sample images are acquired using the same acquisition parameters as used to acquire the plurality of training image pairs.

Abstract: Producing and storing a first image, of a first, initial surface of the specimen; In a primary modification step, modifying said first surface, thereby yielding a second, modified surface; Producing and storing a second image, of said second surface; Using a mathematical Image Similarity Metric to perform pixel-wise comparison of said second and first images, so as to generate a primary figure of merit for said primary modification step.

Abstract: Methods and apparatuses for implementing artificial intelligence enabled volume reconstruction are disclosed herein. An example method at least includes acquiring a first plurality of multi-energy images of a surface of a sample, each image of the first plurality of multi-energy images obtained at a different beam energy, where each image of the first plurality of multi-energy images include data from a different depth within the sample, and reconstructing, by an artificial neural network, at least a volume of the sample based on the first plurality of multi-energy images, where a resolution of the reconstruction is greater than a resolution of the first plurality of multi-energy images.

Abstract: Object tracking using image segmentation is disclosed. A captured image of a specimen is obtained. A segmented image is generated based on the captured image. The segmented image indicates segments corresponding to objects of interest. One or more target objects are identified from the objects of interest in the segmented image. Objects of interest most similar, in position and/or shape, to target objects shown in a previous image may be identified. Alternatively, objects of interest that are associated with connecting vectors most similar to the connecting vectors that connect the target objects in a previous image may be identified. A movement vector is drawn from a target object position in the previous image to a target object position in the segmented image. A field of view of the microscope is moved, with respect to the specimen, according to the movement vector to capture another image of the specimen.

Abstract: Charging areas in electron microscopy are identified by comparing images obtained in different frames. A difference image or one or more optical flow parameters can be used for the comparison. If charging is detected, electron dose is adjusted, typically just in specimen areas associated with charging. Dose is conveniently adjusted by adjusting electron beam dwell time. Upon adjustment, a final image is obtained, with charging effects eliminated or reduced.

Abstract: Techniques for training an artificial neural network (ANN) using simulated specimen images are described. Simulated specimen images are generated based on data models. The data models describe characteristics of a crystalline material and characteristics of one or more defect types. The data models do not include any image data. Simulated specimen images are input as training data into a training algorithm to generate an artificial neural network (ANN) for identifying defects in crystalline materials. After the ANN is trained, the ANN analyzes captured specimen images to identify defects shown therein.

Abstract: Techniques for adapting an adaptive specimen image acquisition system using an artificial neural network (ANN) are disclosed. An adaptive specimen image acquisition system is configurable to scan a specimen to produce images of varying qualities. An adaptive specimen image acquisition system first scans a specimen to produce a low-quality image. An ANN identifies objects of interest within the specimen image. A scan mask indicates regions of the image corresponding to the objects of interest. The adaptive specimen image acquisition system scans only the regions of the image corresponding to the objects of interest, as indicated by the scan mask, to produce a high-quality image. The low-quality image and the high-quality image are merged in a final image. The final image shows the objects of interest at a higher quality, and the rest of the specimen at a lower quality.

Abstract: Charging areas in electron microscopy are identified by comparing images obtained in different frames. A difference image or one or more optical flow parameters can be used for the comparison. If charging is detected, electron dose is adjusted, typically just in specimen areas associated with charging. Dose is conveniently adjusted by adjusting electron beam dwell time. Upon adjustment, a final image is obtained, with charging effects eliminated or reduced.

Abstract: The present invention relates to a method of training a network for reconstructing and/or segmenting microscopic images comprising the step of training the network in the cloud. Further, for training the network in the cloud training data comprising microscopic images can be uploaded into the cloud and a network is trained by the microscopic images. Moreover, for training the network the network can be benchmarked after the reconstructing and/or segmenting of the microscopic images. Wherein for benchmarking the network the quality of the image(s) having undergone the reconstructing and/or segmenting by the network can be compared with the quality of the image(s) having undergone reconstructing and/or segmenting by already known algorithm and/or a second network.

Abstract: Producing and storing a first image, of a first, initial surface of the specimen; In a primary modification step, modifying said first surface, thereby yielding a second, modified surface; Producing and storing a second image, of said second surface; Using a mathematical Image Similarity Metric to perform pixel-wise comparison of said second and first images, so as to generate a primary figure of merit for said primary modification step.

Abstract: A method of investigating a specimen using charged-particle microscopy, and a charged particle microscope configured for same.

Abstract: A method of investigating a specimen using a charged particle microscope, including: Producing and storing a first image, of a first, initial surface of the specimen; In a primary modification step, modifying said first surface, thereby yielding a second, modified surface; Producing and storing a second image, of said second surface; Using a mathematical Image Similarity Metric to perform pixel-wise comparison of said second and first images, so as to generate a primary figure of merit for said primary modification step.

Abstract: The invention relates to a scanning-type charged particle microscope and a method for operation of such a microscope. Disclosed is a novel scanning strategy to the raster scan or serpentine scan. In some embodiment, the beam scanning motion is separated into short-stroke and long-stroke movements, to be assigned to associate short-stroke and long-stroke scanning devices, which may be beam deflectors or stage actuators. The scan strategy which is less susceptible to effects such as overshoot, settling/resynchronization, and “backlash” effects.

Abstract: A Charged Particle Microscope includes A specimen holder, for holding a specimen; A source, for producing a beam of charged particles; An illuminator, for directing said beam so as to irradiate the specimen; and A detector, for detecting a flux of radiation emanating from the specimen in response to said irradiation. The illuminator includes: An aperture plate comprising an aperture region in a path of said beam, for defining a geometry of the beam prior to its impingement upon said specimen. The aperture region includes a distribution of multiple holes, each of which is smaller than a diameter of the beam incident on the aperture plate.

Abstract: Methods of investigating a specimen using tomographic imaging include the following steps. A specimen is provided on a specimen holder and a beam of radiation is directed through the specimen and onto a detector, thereby generating an image of the specimen. The directing is repeated for a set of different specimen orientations relative to the beam, thereby generating a corresponding set of images. An iterative mathematical reconstruction technique is used to convert the set of images into a tomogram of at least a portion of the specimen. The reconstruction is mathematically constrained so as to curtail a solution space resulting therefrom. In addition, three-dimensional SEM imagery of at least a part of the specimen that overlaps at least partially with the portion is obtained.